Kalman filter was pioneered by Rudolf Emil Kalman in 1960, originally designed and developed to solve the navigation problem in Apollo Project. Since then, numerous applications were developed with the implementation of Kalman filter, such as applications in the fields of navigation and computer vision's object tracking. Kalman filter consists of two separate processes, namely the prediction process and the measurement process, which work in a recursive manner. Both processes are modeled by groups of equations in the state space model to achieve optimal estimation outputs. Prior knowledge on the state space model is needed, and it differs between different systems. In this chapter, the authors outlined and explained the fundamental Kalman filtering model in real‐time discrete form and devised two real‐time applications that implemented Kalman filter. The first application involved using vision camera to perform real‐time image processing for vehicle tracking, whereas the second application discussed the real‐time Global Positioning System (GPS)‐aided Strapdown Inertial Navigation Unit (SINU) system implementation using Kalman filter. Detail descriptions, model derivations, and results are outlined in both applications.
Part of the book: Real-time Systems